© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 155
    Prev
    Next
    INDEX
    Explanations

    terms related to recipe instructions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    168
    +0.09
    0.3%
    1677
    +0.09
    0.3%
    1052
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.09
    0.03
    1052
    +0.09
    0.02
    184
    +0.09
    0.01
    Negative Logits
    <bos>
    -0.90
     fix
    -0.67
     por
    -0.61
     earn
    -0.61
    private
    -0.60
    function
    -0.60
     put
    -0.60
     off
    -0.59
    func
    -0.58
     go
    -0.58
    POSITIVE LOGITS
     Campbell
    1.88
    Campbell
    1.71
     ftu
    1.64
     depic
    1.61
     effe
    1.61
     saar
    1.60
     maneu
    1.58
     CAMPBELL
    1.57
     stockholm
    1.55
     vns
    1.53
    Activations Density 0.207%

    No Known Activations